Pattern recognition utilizing a nanotechnology-based neural network

Abstract

A pattern recognition system, comprising a neural network formed utilizing nanotechnology and a pattern input unit, which communicates with the neural network, wherein the neural network processes data input via the pattern input unit in order to recognize data patterns thereof. Such a pattern recognition system can be implemented in the context of a speech recognition system and / or other pattern recognition systems, such as visual and / or imaging recognition systems.

Description

CROSS REFERENCE TO RELATED PATENT APPLICATION [0001] This patent application is a continuation of U.S. patent application Ser. No. 10 / 095,273 entitled “Physical Neural Network Design Incorporating Nanotechnology,” which was filed on Mar. 12, 2002, the disclosure of which is incorporated herein by reference in its entirety.TECHNICAL FIELD [0002] Embodiments generally relate to nanotechnology. Embodiments also relate to neural networks and neural computing systems and methods thereof. Embodiments also relate to pattern recognition devices, methods and systems, including devices that recognize speech, visual and / or imaging data. BACKGROUND [0003] Neural networks are computational systems that permit computers to essentially function in a manner analogous to that of the human brain. Neural networks do not utilize the traditional digital model of manipulating 0's and 1's. Instead, neural networks create connections between processing elements, which are equivalent to neurons of a human b...

AI Technical Summary

Benefits of technology

This approach enables the creation of large, trainable neural networks without the need for computer simulations, facilitating efficient pattern recognition in speech, visual, and imaging data, with the potential for significant advancements in neural network capabilities.

Problems solved by technology

The implementation of neural network systems has lagged somewhat behind their theoretical potential due to the difficulties in building neural network hardware.

Due to the difficulties in building such highly interconnected processors, the currently available neural network hardware systems have not approached this level of complexity.

Another disadvantage of hardware systems is that they typically are often custom designed and built to implement one particular neural network architecture and are not easily, if at all, reconfigurable to implement different architectures.

A true physical neural network (i.e., artificial neural network) chip, for example, has not yet been designed and successfully implemented.

The problem with a pure hardware implementation of a neural network with technology as it exists today, is the inability to physically form a great number of connections and neurons.

On-chip learning can exist, but the size of the network would be limited by digital processing methods and associated electronic circuitry.

One of the difficulties in creating true physical neural networks lies in the highly complex manner in which a physical neural network must be designed and built.

Images